ENH: micro perf tweaks to speed up DataFrame constructor, unit testing

pandas/core/common.py

@@ -585,10 +585,12 @@ def _is_bool_indexer(key):
 
     return False
 
-
 def _default_index(n):
-    from pandas.core.index import Index
-    return Index(np.arange(n))
+    from pandas.core.index import Int64Index
+    values = np.arange(n)
+    result = values.view(Int64Index)
+    result.name = None
+    return result
 
 
 def ensure_float(arr):

pandas/core/frame.py

@@ -27,8 +27,7 @@
 from pandas.core.generic import NDFrame
 from pandas.core.index import Index, MultiIndex, _ensure_index
 from pandas.core.indexing import _NDFrameIndexer, _maybe_droplevels
-from pandas.core.internals import (BlockManager, make_block, form_blocks,
-                                   IntBlock)
+from pandas.core.internals import BlockManager, make_block, form_blocks
 from pandas.core.series import Series, _radd_compat, _dtype_from_scalar
 from pandas.compat.scipy import scoreatpercentile as _quantile
 from pandas.util import py3compat

pandas/core/generic.py

@@ -482,8 +482,8 @@ def __init__(self, data, axes=None, copy=False, dtype=None):
             for i, ax in enumerate(axes):
                 data = data.reindex_axis(ax, axis=i)
 
-        self._data = data
-        self._item_cache = {}
+        object.__setattr__(self, '_data', data)
+        object.__setattr__(self, '_item_cache', {})
 
     def astype(self, dtype):
         """

pandas/util/testing.py

@@ -23,7 +23,6 @@
 from pandas import bdate_range
 from pandas.tseries.index import DatetimeIndex
 from pandas.tseries.period import PeriodIndex
-from pandas.tseries.interval import IntervalIndex
 
 Index = index.Index
 Series = series.Series
@@ -96,7 +95,7 @@ def assert_almost_equal(a, b):
 
     if isiterable(a):
         np.testing.assert_(isiterable(b))
-        np.testing.assert_equal(len(a), len(b))
+        assert(len(a) == len(b))
         if np.array_equal(a, b):
             return True
         else:

vb_suite/ctors.py

@@ -15,3 +15,11 @@
 series_constructor_ndarray = \
     Benchmark("Series(data, index=index)", setup=setup,
               name='series_constructor_ndarray')
+
+setup = common_setup + """
+arr = np.random.randn(100, 100)
+"""
+
+frame_constructor_ndarray = \
+    Benchmark("DataFrame(arr)", setup=setup,
+              name='frame_constructor_ndarray')